EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
2060. Comparison of risk-minimization portfolios with cardinality constraints and period lengths
Invited abstract in session MB-51: Market risk in a volatile world, stream Risk management in finance.
Monday, 10:30-12:00Room: M5 (building: 101)
Authors (first author is the speaker)
| 1. | Aleš Kresta
|
| Department of Finance, Faculty of Economics, VSB-Technical University of Ostrava | |
| 2. | Qian Gao
|
| VSB - Technical University of Ostrava |
Abstract
In this study, we empirically compare the performance of portfolios optimized to minimise selected risk measures under a cardinality constraint. The chosen risk measures include standard deviation, semi-deviation, minimax, mean absolute deviation, maximum drawdown, conditional value at risk, and entropic value at risk. Additionally, we introduce different values of the cardinality constraint and vary the period length used for parameter estimation in the portfolio optimisation problem. This approach allows for a comprehensive comparison of risk-minimization portfolios, taking into account the selected risk measure, cardinality constraint, and period length simultaneously. Furthermore, we evaluate portfolio performance under various market conditions, specifically in the United States, Germany, and Chinese stock markets. Evaluation metrics include the Sharpe ratio, the Sortino ratio, and the Calmar ratio. The results reveal that no single risk measure dominates the others, and significant differences exist among them. Although the durations of optimal estimation periods vary for different risk measures, certain patterns emerge from the findings.
Keywords
- Risk Analysis and Management
- Financial Modelling
- Finance and Banking
Status: accepted
Back to the list of papers